INDEX

Explanations

programming-related terminology, particularly variable declarations and annotations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.16

ello

-0.15

åĿª

-0.15

 ê²Įìĭľë¬¼

-0.14

lbrace

-0.14

stor

-0.14

-0.13

/aws

-0.13

POSITIVE LOGITS

nullable

0.21

 nullable

0.18

Nullable

0.16

SerializedName

0.16

(nullable

0.16

veis

0.16

ORIGINAL

0.15

Nak

0.15

Gin

0.15

 pros

0.15

Activations Density 0.017%

programming-related terminology, particularly variable declarations and annotations

No Comments

No Known Activations